# Generative AI for software development

This covers a lot of the same ground as some of the Takeoff courses, but the fact that the Takeoff ones assume that you're working in an IDE that integrates the models means that everything works better there. In this course, the content is generally more shallow and requires more effort to make work. For example, file tagging in Cursor gives you a quick way to assign a role to the model, along with detailed instructions on exactly how you want it to fulfil that role. Takeoff also has you producing functional apps rather than tweaking basic algorithms.

On the plus side, this course has more emphasis on analyzing and improving the generated code (even if the actual suggestions for how to do so aren't as detailed). It also has practice quizzes (though like with all Coursera courses, not enough) and the programming exercises are marked, which forces you to go through with them and provides objective feedback.

The only major disagreement that I have is that the course puts a lot of emphasis on [persona prompting](#user-content-fn-1)[^1], which I think is probably neutral to detrimental when working with the most advanced models. Telling it to focus on the security side (for example) might be helpful, but you need to make sure that you're getting it to think like an expert rather than roleplay a superficial stereotype of an expert.

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td></td><td>Introduction to generative AI for software development</td><td></td><td><a href="/pages/FcGVCnoP738Av9mRaUVg">/pages/FcGVCnoP738Av9mRaUVg</a></td><td><a href="/files/UHF7zjwcq36zmrwja3ub">/files/UHF7zjwcq36zmrwja3ub</a></td></tr><tr><td></td><td>Team software engineering with AI</td><td></td><td><a href="/pages/aUlowrt3x1lUPGTQl640">/pages/aUlowrt3x1lUPGTQl640</a></td><td><a href="/files/vxs1ER5I8VkIA0IaOqfo">/files/vxs1ER5I8VkIA0IaOqfo</a></td></tr><tr><td></td><td>AI-powered software and system design</td><td></td><td><a href="/pages/ECCDpIZdSUbvh9O7bC9U">/pages/ECCDpIZdSUbvh9O7bC9U</a></td><td><a href="/files/WqTZslyWgLz3XWQj63oY">/files/WqTZslyWgLz3XWQj63oY</a></td></tr></tbody></table>

[^1]: "You are an expert \[insert role here]..."


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://www.raoulharris.com/technical-courses/generative-ai-for-software-development.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.